The core of video understanding tasks, such as recognition, captioning, and tracking, is to automatically detect objects or actions in a video and analyze their temporal evolution. Despite sharing a common goal, different tasks often rely on distinct model architectures and annotation formats. In contrast, natural language processing benefits from a unified output space, i.e., text sequences, which simplifies the training of powerful foundational language models, such as GPT-3, with extensive training corpora. Inspired by this, we seek to unify the output space of video understanding tasks by using languages as labels and additionally introducing time and box tokens. In this way, a variety of video tasks could be formulated as video-grounded token generation. This enables us to address various types of video tasks, including classification (such as action recognition), captioning (covering clip captioning, video question answering, and dense video captioning), and localization tasks (such as visual object tracking) within a fully shared encoder-decoder architecture, following a generative framework. Through comprehensive experiments, we demonstrate such a simple and straightforward idea is quite effective and can achieve state-of-the-art or competitive results on seven video benchmarks, providing a novel perspective for more universal video understanding. Code is available at https://github.com/wangjk666/OmniVid.

翻译：视频理解任务的核心，如识别、描述和跟踪，在于自动检测视频中的对象或动作，并分析其时间演化过程。尽管目标一致，但不同任务通常依赖不同的模型架构和标注格式。相比之下，自然语言处理受益于统一的输出空间——文本序列，这使得强大基础语言模型（如GPT-3）能够通过大规模训练语料库进行训练。受此启发，我们尝试通过使用语言作为标签，并额外引入时间标记和边界框标记，统一视频理解任务的输出空间。这样，多种视频任务可被公式化为基于视频的标记生成。这使我们能够在一个完全共享的编码器-解码器架构中，遵循生成式框架，处理多种类型的视频任务，包括分类（如动作识别）、描述（涵盖片段描述、视频问答和密集视频描述）以及定位任务（如视觉对象跟踪）。通过全面实验，我们证明了这一简单直接的想法非常有效，能够在七个视频基准上取得最先进或具有竞争力的结果，为更通用的视频理解提供了新视角。代码已开源：https://github.com/wangjk666/OmniVid。